The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data via the $ARGUMENTS variable and interpolates it into a JSON payload for a Discord webhook request.\n
Ingestion points: $ARGUMENTS variable in SKILL.md.\n
Boundary markers: None present to delimit user input from instructions.\n
Capability inventory: Execution of curl via the Bash tool to perform network requests.\n
Sanitization: No explicit sanitization or validation logic is defined within the skill instructions, although the reference documentation mentions it as a consideration.\n- [COMMAND_EXECUTION]: The skill uses curl to transmit data. Constructing shell commands using dynamically generated JSON bodies from user-provided arguments creates a risk of command injection if the agent does not properly escape the content.

notify-discord